Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

Changes of note:

 1) Allow to schedule ICMP packets in IPVS, from Alex Gartrell.

 2) Provide FIB table ID in ipv4 route dumps just as ipv6 does, from
    David Ahern.

 3) Allow the user to ask for the statistics to be filtered out of
    ipv4/ipv6 address netlink dumps.  From Sowmini Varadhan.

 4) More work to pass the network namespace context around deep into
    various packet path APIs, starting with the netfilter hooks.  From
    Eric W Biederman.

 5) Add layer 2 TX/RX checksum offloading to qeth driver, from Thomas
    Richter.

 6) Use usec resolution for SYN/ACK RTTs in TCP, from Yuchung Cheng.

 7) Support Very High Throughput in wireless MESH code, from Bob
    Copeland.

 8) Allow setting the ageing_time in switchdev/rocker.  From Scott
    Feldman.

 9) Properly autoload L2TP type modules, from Stephen Hemminger.

10) Fix and enable offload features by default in 8139cp driver, from
    David Woodhouse.

11) Support both ipv4 and ipv6 sockets in a single vxlan device, from
    Jiri Benc.

12) Fix CWND limiting of thin streams in TCP, from Bendik Rønning
    Opstad.

13) Fix IPSEC flowcache overflows on large systems, from Steffen
    Klassert.

14) Convert bridging to track VLANs using rhashtable entries rather than
    a bitmap.  From Nikolay Aleksandrov.

15) Make TCP listener handling completely lockless, this is a major
    accomplishment.  Incoming request sockets now live in the
    established hash table just like any other socket too.

    From Eric Dumazet.

15) Provide more bridging attributes to netlink, from Nikolay
    Aleksandrov.

16) Use hash based algorithm for ipv4 multipath routing, this was very
    long overdue.  From Peter Nørlund.

17) Several y2038 cures, mostly avoiding timespec.  From Arnd Bergmann.

18) Allow non-root execution of EBPF programs, from Alexei Starovoitov.

19) Support SO_INCOMING_CPU as setsockopt, from Eric Dumazet.  This
    influences the port binding selection logic used by SO_REUSEPORT.

20) Add ipv6 support to VRF, from David Ahern.

21) Add support for Mellanox Spectrum switch ASIC, from Jiri Pirko.

22) Add rtl8xxxu Realtek wireless driver, from Jes Sorensen.

23) Implement RACK loss recovery in TCP, from Yuchung Cheng.

24) Support multipath routes in MPLS, from Roopa Prabhu.

25) Fix POLLOUT notification for listening sockets in AF_UNIX, from Eric
    Dumazet.

26) Add new QED Qlogic river, from Yuval Mintz, Manish Chopra, and
    Sudarsana Kalluru.

27) Don't fetch timestamps on AF_UNIX sockets, from Hannes Frederic
    Sowa.

28) Support ipv6 geneve tunnels, from John W Linville.

29) Add flood control support to switchdev layer, from Ido Schimmel.

30) Fix CHECKSUM_PARTIAL handling of potentially fragmented frames, from
    Hannes Frederic Sowa.

31) Support persistent maps and progs in bpf, from Daniel Borkmann.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1790 commits)
  sh_eth: use DMA barriers
  switchdev: respect SKIP_EOPNOTSUPP flag in case there is no recursion
  net: sched: kill dead code in sch_choke.c
  irda: Delete an unnecessary check before the function call "irlmp_unregister_service"
  net: dsa: mv88e6xxx: include DSA ports in VLANs
  net: dsa: mv88e6xxx: disable SA learning for DSA and CPU ports
  net/core: fix for_each_netdev_feature
  vlan: Invoke driver vlan hooks only if device is present
  arcnet/com20020: add LEDS_CLASS dependency
  bpf, verifier: annotate verbose printer with __printf
  dp83640: Only wait for timestamps for packets with timestamping enabled.
  ptp: Change ptp_class to a proper bitmask
  dp83640: Prune rx timestamp list before reading from it
  dp83640: Delay scheduled work.
  dp83640: Include hash in timestamp/packet matching
  ipv6: fix tunnel error handling
  net/mlx5e: Fix LSO vlan insertion
  net/mlx5e: Re-eanble client vlan TX acceleration
  net/mlx5e: Return error in case mlx5e_set_features() fails
  net/mlx5e: Don't allow more than max supported channels
  ...

1 files changed, 66 insertions, 25 deletions

diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index d99c116032f3..44462b40f2d7 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -536,6 +536,7 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type)
 	}
 	if (type == I40E_VSI_SRIOV) {
 		u8 brdcast[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
+
 		vf->lan_vsi_idx = vsi->idx;
 		vf->lan_vsi_id = vsi->id;
 		/* If the port VLAN has been configured and then the
@@ -546,6 +547,8 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type)
 		 */
 		if (vf->port_vlan_id)
 			i40e_vsi_add_pvid(vsi, vf->port_vlan_id);
+
+		spin_lock_bh(&vsi->mac_filter_list_lock);
 		f = i40e_add_filter(vsi, vf->default_lan_addr.addr,
 				    vf->port_vlan_id ? vf->port_vlan_id : -1,
 				    true, false);
@@ -558,10 +561,11 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type)
 		if (!f)
 			dev_info(&pf->pdev->dev,
 				 "Could not allocate VF broadcast filter\n");
+		spin_unlock_bh(&vsi->mac_filter_list_lock);
 	}
 
 	/* program mac filter */
-	ret = i40e_sync_vsi_filters(vsi);
+	ret = i40e_sync_vsi_filters(vsi, false);
 	if (ret)
 		dev_err(&pf->pdev->dev, "Unable to program ucast filters\n");
 
@@ -605,6 +609,7 @@ static void i40e_enable_vf_mappings(struct i40e_vf *vf)
 	/* map PF queues to VF queues */
 	for (j = 0; j < pf->vsi[vf->lan_vsi_idx]->alloc_queue_pairs; j++) {
 		u16 qid = i40e_vc_get_pf_queue_id(vf, vf->lan_vsi_id, j);
+
 		reg = (qid & I40E_VPLAN_QTABLE_QINDEX_MASK);
 		wr32(hw, I40E_VPLAN_QTABLE(total_queue_pairs, vf->vf_id), reg);
 		total_queue_pairs++;
@@ -701,6 +706,7 @@ static void i40e_free_vf_res(struct i40e_vf *vf)
 	 */
 	vf->num_queue_pairs = 0;
 	vf->vf_states = 0;
+	clear_bit(I40E_VF_STAT_INIT, &vf->vf_states);
 }
 
 /**
@@ -839,11 +845,11 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr)
 complete_reset:
 	/* reallocate VF resources to reset the VSI state */
 	i40e_free_vf_res(vf);
-	i40e_alloc_vf_res(vf);
-	i40e_enable_vf_mappings(vf);
-	set_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states);
-	clear_bit(I40E_VF_STAT_DISABLED, &vf->vf_states);
-
+	if (!i40e_alloc_vf_res(vf)) {
+		i40e_enable_vf_mappings(vf);
+		set_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states);
+		clear_bit(I40E_VF_STAT_DISABLED, &vf->vf_states);
+	}
 	/* tell the VF the reset is done */
 	wr32(hw, I40E_VFGEN_RSTAT1(vf->vf_id), I40E_VFR_VFACTIVE);
 	i40e_flush(hw);
@@ -872,6 +878,11 @@ void i40e_free_vfs(struct i40e_pf *pf)
 			i40e_vsi_control_rings(pf->vsi[pf->vf[i].lan_vsi_idx],
 					       false);
 
+	for (i = 0; i < pf->num_alloc_vfs; i++)
+		if (test_bit(I40E_VF_STAT_INIT, &pf->vf[i].vf_states))
+			i40e_vsi_control_rings(pf->vsi[pf->vf[i].lan_vsi_idx],
+					       false);
+
 	/* Disable IOV before freeing resources. This lets any VF drivers
 	 * running in the host get themselves cleaned up before we yank
 	 * the carpet out from underneath their feet.
@@ -933,6 +944,7 @@ int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs)
 	if (pci_num_vf(pf->pdev) != num_alloc_vfs) {
 		ret = pci_enable_sriov(pf->pdev, num_alloc_vfs);
 		if (ret) {
+			pf->flags &= ~I40E_FLAG_VEB_MODE_ENABLED;
 			pf->num_alloc_vfs = 0;
 			goto err_iov;
 		}
@@ -957,8 +969,6 @@ int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs)
 		/* VF resources get allocated during reset */
 		i40e_reset_vf(&vfs[i], false);
 
-		/* enable VF vplan_qtable mappings */
-		i40e_enable_vf_mappings(&vfs[i]);
 	}
 	pf->num_alloc_vfs = num_alloc_vfs;
 
@@ -986,24 +996,26 @@ static int i40e_pci_sriov_enable(struct pci_dev *pdev, int num_vfs)
 	int pre_existing_vfs = pci_num_vf(pdev);
 	int err = 0;
 
-	if (pf->state & __I40E_TESTING) {
+	if (test_bit(__I40E_TESTING, &pf->state)) {
 		dev_warn(&pdev->dev,
 			 "Cannot enable SR-IOV virtual functions while the device is undergoing diagnostic testing\n");
 		err = -EPERM;
 		goto err_out;
 	}
 
-	dev_info(&pdev->dev, "Allocating %d VFs.\n", num_vfs);
 	if (pre_existing_vfs && pre_existing_vfs != num_vfs)
 		i40e_free_vfs(pf);
 	else if (pre_existing_vfs && pre_existing_vfs == num_vfs)
 		goto out;
 
 	if (num_vfs > pf->num_req_vfs) {
+		dev_warn(&pdev->dev, "Unable to enable %d VFs. Limited to %d VFs due to device resource constraints.\n",
+			 num_vfs, pf->num_req_vfs);
 		err = -EPERM;
 		goto err_out;
 	}
 
+	dev_info(&pdev->dev, "Allocating %d VFs.\n", num_vfs);
 	err = i40e_alloc_vfs(pf, num_vfs);
 	if (err) {
 		dev_warn(&pdev->dev, "Failed to enable SR-IOV: %d\n", err);
@@ -1094,6 +1106,8 @@ static int i40e_vc_send_msg_to_vf(struct i40e_vf *vf, u32 v_opcode,
 		}
 	} else {
 		vf->num_valid_msgs++;
+		/* reset the invalid counter, if a valid message is received. */
+		vf->num_invalid_msgs = 0;
 	}
 
 	aq_ret = i40e_aq_send_msg_to_vf(hw, abs_vf_id,	v_opcode, v_retval,
@@ -1195,16 +1209,22 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg)
 	} else {
 		vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_RSS_REG;
 	}
+
+	if (vf->driver_caps & I40E_VIRTCHNL_VF_OFFLOAD_RX_POLLING)
+		vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_RX_POLLING;
+
 	vfres->num_vsis = num_vsis;
 	vfres->num_queue_pairs = vf->num_queue_pairs;
 	vfres->max_vectors = pf->hw.func_caps.num_msix_vectors_vf;
 	if (vf->lan_vsi_idx) {
 		vfres->vsi_res[i].vsi_id = vf->lan_vsi_id;
 		vfres->vsi_res[i].vsi_type = I40E_VSI_SRIOV;
-		vfres->vsi_res[i].num_queue_pairs =
-		    pf->vsi[vf->lan_vsi_idx]->alloc_queue_pairs;
-		memcpy(vfres->vsi_res[i].default_mac_addr,
-		       vf->default_lan_addr.addr, ETH_ALEN);
+		vfres->vsi_res[i].num_queue_pairs = vsi->alloc_queue_pairs;
+		/* VFs only use TC 0 */
+		vfres->vsi_res[i].qset_handle
+					  = le16_to_cpu(vsi->info.qs_handle[0]);
+		ether_addr_copy(vfres->vsi_res[i].default_mac_addr,
+				vf->default_lan_addr.addr);
 		i++;
 	}
 	set_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states);
@@ -1582,6 +1602,11 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 	}
 	vsi = pf->vsi[vf->lan_vsi_idx];
 
+	/* Lock once, because all function inside for loop accesses VSI's
+	 * MAC filter list which needs to be protected using same lock.
+	 */
+	spin_lock_bh(&vsi->mac_filter_list_lock);
+
 	/* add new addresses to the list */
 	for (i = 0; i < al->num_elements; i++) {
 		struct i40e_mac_filter *f;
@@ -1600,12 +1625,14 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 			dev_err(&pf->pdev->dev,
 				"Unable to add VF MAC filter\n");
 			ret = I40E_ERR_PARAM;
+			spin_unlock_bh(&vsi->mac_filter_list_lock);
 			goto error_param;
 		}
 	}
+	spin_unlock_bh(&vsi->mac_filter_list_lock);
 
 	/* program the updated filter list */
-	if (i40e_sync_vsi_filters(vsi))
+	if (i40e_sync_vsi_filters(vsi, false))
 		dev_err(&pf->pdev->dev, "Unable to program VF MAC filters\n");
 
 error_param:
@@ -1650,13 +1677,15 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 	}
 	vsi = pf->vsi[vf->lan_vsi_idx];
 
+	spin_lock_bh(&vsi->mac_filter_list_lock);
 	/* delete addresses from the list */
 	for (i = 0; i < al->num_elements; i++)
 		i40e_del_filter(vsi, al->list[i].addr,
 				I40E_VLAN_ANY, true, false);
+	spin_unlock_bh(&vsi->mac_filter_list_lock);
 
 	/* program the updated filter list */
-	if (i40e_sync_vsi_filters(vsi))
+	if (i40e_sync_vsi_filters(vsi, false))
 		dev_err(&pf->pdev->dev, "Unable to program VF MAC filters\n");
 
 error_param:
@@ -1708,6 +1737,7 @@ static int i40e_vc_add_vlan_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 	for (i = 0; i < vfl->num_elements; i++) {
 		/* add new VLAN filter */
 		int ret = i40e_vsi_add_vlan(vsi, vfl->vlan_id[i]);
+
 		if (ret)
 			dev_err(&pf->pdev->dev,
 				"Unable to add VF vlan filter %d, error %d\n",
@@ -1759,6 +1789,7 @@ static int i40e_vc_remove_vlan_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 
 	for (i = 0; i < vfl->num_elements; i++) {
 		int ret = i40e_vsi_kill_vlan(vsi, vfl->vlan_id[i]);
+
 		if (ret)
 			dev_err(&pf->pdev->dev,
 				"Unable to delete VF vlan filter %d, error %d\n",
@@ -1870,7 +1901,6 @@ static int i40e_vc_validate_vf_msg(struct i40e_vf *vf, u32 v_opcode,
 	case I40E_VIRTCHNL_OP_UNKNOWN:
 	default:
 		return -EPERM;
-		break;
 	}
 	/* few more checks */
 	if ((valid_len != msglen) || (err_msg_format)) {
@@ -2049,6 +2079,11 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 		goto error_param;
 	}
 
+	/* Lock once because below invoked function add/del_filter requires
+	 * mac_filter_list_lock to be held
+	 */
+	spin_lock_bh(&vsi->mac_filter_list_lock);
+
 	/* delete the temporary mac address */
 	i40e_del_filter(vsi, vf->default_lan_addr.addr,
 			vf->port_vlan_id ? vf->port_vlan_id : -1,
@@ -2060,9 +2095,11 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 	list_for_each_entry(f, &vsi->mac_filter_list, list)
 		i40e_del_filter(vsi, f->macaddr, f->vlan, true, false);
 
+	spin_unlock_bh(&vsi->mac_filter_list_lock);
+
 	dev_info(&pf->pdev->dev, "Setting MAC %pM on VF %d\n", mac, vf_id);
 	/* program mac filter */
-	if (i40e_sync_vsi_filters(vsi)) {
+	if (i40e_sync_vsi_filters(vsi, false)) {
 		dev_err(&pf->pdev->dev, "Unable to program ucast filters\n");
 		ret = -EIO;
 		goto error_param;
@@ -2089,8 +2126,10 @@ error_param:
 int i40e_ndo_set_vf_port_vlan(struct net_device *netdev,
 			      int vf_id, u16 vlan_id, u8 qos)
 {
+	u16 vlanprio = vlan_id | (qos << I40E_VLAN_PRIORITY_SHIFT);
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_pf *pf = np->vsi->back;
+	bool is_vsi_in_vlan = false;
 	struct i40e_vsi *vsi;
 	struct i40e_vf *vf;
 	int ret = 0;
@@ -2116,12 +2155,15 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev,
 		goto error_pvid;
 	}
 
-	if (le16_to_cpu(vsi->info.pvid) ==
-	    (vlan_id | (qos << I40E_VLAN_PRIORITY_SHIFT)))
+	if (le16_to_cpu(vsi->info.pvid) == vlanprio)
 		/* duplicate request, so just return success */
 		goto error_pvid;
 
-	if (le16_to_cpu(vsi->info.pvid) == 0 && i40e_is_vsi_in_vlan(vsi)) {
+	spin_lock_bh(&vsi->mac_filter_list_lock);
+	is_vsi_in_vlan = i40e_is_vsi_in_vlan(vsi);
+	spin_unlock_bh(&vsi->mac_filter_list_lock);
+
+	if (le16_to_cpu(vsi->info.pvid) == 0 && is_vsi_in_vlan) {
 		dev_err(&pf->pdev->dev,
 			"VF %d has already configured VLAN filters and the administrator is requesting a port VLAN override.\nPlease unload and reload the VF driver for this change to take effect.\n",
 			vf_id);
@@ -2141,7 +2183,7 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev,
 	 * MAC addresses deleted.
 	 */
 	if ((!(vlan_id || qos) ||
-	    (vlan_id | qos) != le16_to_cpu(vsi->info.pvid)) &&
+	    vlanprio != le16_to_cpu(vsi->info.pvid)) &&
 	    vsi->info.pvid)
 		ret = i40e_vsi_add_vlan(vsi, I40E_VLAN_ANY);
 
@@ -2156,8 +2198,7 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev,
 		}
 	}
 	if (vlan_id || qos)
-		ret = i40e_vsi_add_pvid(vsi,
-				vlan_id | (qos << I40E_VLAN_PRIORITY_SHIFT));
+		ret = i40e_vsi_add_pvid(vsi, vlanprio);
 	else
 		i40e_vsi_remove_pvid(vsi);
 
@@ -2310,7 +2351,7 @@ int i40e_ndo_get_vf_config(struct net_device *netdev,
 
 	ivi->vf = vf_id;
 
-	memcpy(&ivi->mac, vf->default_lan_addr.addr, ETH_ALEN);
+	ether_addr_copy(ivi->mac, vf->default_lan_addr.addr);
 
 	ivi->max_tx_rate = vf->tx_rate;
 	ivi->min_tx_rate = 0;